A Data Recovery Algorithm Based on Compressive Sensing in Wireless Sensor Network
LI Yan-pin · Jisuanji gongcheng · 2014
In Wireless Sensor Network(WSN),since many applications heavily rely on the complete sensory data,several works have studied preventing the data loss problem.However,existing solutions cannot achieve satisfactory accuracy due to special loss patterns and high loss rates in WSN.In this work,based on two real datasets,the Intel Indoor project and the GreenOrbs project,they reveal that such correlations are strong,such as,the change of temperature and light illumination.Motivated by this observation,this paper proposes a Multi-attribute-assistant Compressive-Sensing-based(MACS) algorithm to optimize the recovery accuracy.Real trace-driven simulation is performed.Simulation results show that MACS outperforms the existing solutions.Typically,MACS can recover all data with less than5%error when the loss rate is less than 60%.Even when losing 85%data,all missing data can be estimated by MACS with less than 10%error.